Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    political news and developments

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    unts
    -0.92
    aster
    -0.85
    oller
    -0.83
    iop
    -0.82
    ogun
    -0.81
    axe
    -0.79
     cloves
    -0.78
     nuts
    -0.78
    士
    -0.77
    è¦ļéĨĴ
    -0.76
    POSITIVE LOGITS
     Continued
    0.98
     Transcript
    0.96
     Cohn
    0.90
    ancies
    0.90
     ï
    0.89
    EStream
    0.88
    CLASSIFIED
    0.87
     McCain
    0.84
    ...]
    0.81
     arri
    0.81
    Act Density 0.041%

    No Known Activations